<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Neural Network classification problems in SAS Data Science</title>
    <link>https://communities.sas.com/t5/SAS-Data-Science/Neural-Network-classification-problems/m-p/71727#M447</link>
    <description>Hi Guys,&lt;BR /&gt;
I have run the Neural network for the purpose of classification.&lt;BR /&gt;
however, after training the data , I have found the mis-classification&lt;BR /&gt;
numbers are quit high.&lt;BR /&gt;
&lt;BR /&gt;
Just wondering what do your guys deal with this when this thing&lt;BR /&gt;
happened?&lt;BR /&gt;
What factors would influence the results.&lt;BR /&gt;
I am using the results from text mining to train my data. so I used&lt;BR /&gt;
the SVDs as input to train data.&lt;BR /&gt;
so my input is 100 SVDs and target is the classification categories it&lt;BR /&gt;
is about 23 clusters. i have tried setting the network from 6 hidden&lt;BR /&gt;
neuro to 40 neuros.&lt;BR /&gt;
&lt;BR /&gt;
please help.&lt;BR /&gt;
&lt;BR /&gt;
any suggestions and ideas are fine.&lt;BR /&gt;
&lt;BR /&gt;
thanks.</description>
    <pubDate>Wed, 16 Sep 2009 14:43:17 GMT</pubDate>
    <dc:creator>nernernini</dc:creator>
    <dc:date>2009-09-16T14:43:17Z</dc:date>
    <item>
      <title>Neural Network classification problems</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/Neural-Network-classification-problems/m-p/71727#M447</link>
      <description>Hi Guys,&lt;BR /&gt;
I have run the Neural network for the purpose of classification.&lt;BR /&gt;
however, after training the data , I have found the mis-classification&lt;BR /&gt;
numbers are quit high.&lt;BR /&gt;
&lt;BR /&gt;
Just wondering what do your guys deal with this when this thing&lt;BR /&gt;
happened?&lt;BR /&gt;
What factors would influence the results.&lt;BR /&gt;
I am using the results from text mining to train my data. so I used&lt;BR /&gt;
the SVDs as input to train data.&lt;BR /&gt;
so my input is 100 SVDs and target is the classification categories it&lt;BR /&gt;
is about 23 clusters. i have tried setting the network from 6 hidden&lt;BR /&gt;
neuro to 40 neuros.&lt;BR /&gt;
&lt;BR /&gt;
please help.&lt;BR /&gt;
&lt;BR /&gt;
any suggestions and ideas are fine.&lt;BR /&gt;
&lt;BR /&gt;
thanks.</description>
      <pubDate>Wed, 16 Sep 2009 14:43:17 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/Neural-Network-classification-problems/m-p/71727#M447</guid>
      <dc:creator>nernernini</dc:creator>
      <dc:date>2009-09-16T14:43:17Z</dc:date>
    </item>
    <item>
      <title>Re: Neural Network classification problems</title>
      <link>https://communities.sas.com/t5/SAS-Data-Science/Neural-Network-classification-problems/m-p/71728#M448</link>
      <description>Hello.  To try to help, we need to know a little more about your data.  What generated the target columns?  How is it related to the text data ?  Have you tried any other modeling techniques ?  Cheers.</description>
      <pubDate>Wed, 21 Oct 2009 20:45:55 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Data-Science/Neural-Network-classification-problems/m-p/71728#M448</guid>
      <dc:creator>David_Duling</dc:creator>
      <dc:date>2009-10-21T20:45:55Z</dc:date>
    </item>
  </channel>
</rss>

